© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89421
    Prev
    Next
    INDEX
    Explanations

    terms related to criminal activities and legal violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    @student
    -0.08
     italia
    -0.07
    FINE
    -0.07
    enant
    -0.07
    interpreter
    -0.07
    anders
    -0.07
    <?,
    -0.07
    окÑĥ
    -0.07
    _notifier
    -0.07
    preter
    -0.07
    POSITIVE LOGITS
     charges
    0.07
     charge
    0.07
    wer
    0.07
    lant
    0.07
    729
    0.06
     earlier
    0.06
     e
    0.06
     and
    0.06
    itr
    0.06
    -related
    0.06
    Activations Density 0.018%

    No Known Activations